Evals
Reward
Evaluate LLM output against specified criteria. Score on a continuous 0-1 scale.
POST
Authorizations
Body
application/json
Request model for reward score evaluation of LLM responses against specified criteria.
A list of messages in OpenAI format
Represents a single message in a conversation.
Criteria used for evaluation. Begins with 'Reward responses' or 'Penalize responses'